[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-bytedance-seed3d-2-0-moe-3d-generation":3,"topics-all":36,"news-related-e14bd6f5-912c-435e-8a95-fe6de3de33e9":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"e14bd6f5-912c-435e-8a95-fe6de3de33e9","字节跳动发布Seed3D 2.0：3D生成模型的新突破","字节跳动近日发布新一代3D生成大模型Seed3D 2.0，采用MoE架构和稀疏专家路由技术，在扩大参数量和分辨率的同时控制推理计算量，实现更丰富的纹理细节和更精确的金属-粗糙度边界生成。\n\n**技术创新亮点**\n\nSeed3D 2.0的核心突破在于其Mixture of Experts架构。通过稀疏专家路由机制，模型能够在保持高精度的同时，有效控制计算复杂度。这种设计使得模型能够处理更复杂的3D场景，生成质量显著提升，特别是在材质表现和细节还原方面表现突出。\n\n**实用价值显著**\n\n相比传统3D生成模型，Seed3D 2.0在实用性和可用性方面大幅改进。技术报告显示，该模型在复杂场景渲染、细节表现等方面均有显著提升，为游戏开发、虚拟现实、工业设计等领域提供了强有力的技术支撑。\n\n**推动行业生态发展**\n\n随着API在火山引擎上线，Seed3D 2.0的发布将推动整个3D内容生成生态的发展。开发者和企业将更容易获得高质量的3D生成能力，加速3D内容在各行业的普及应用，展现了中国企业在AI基础模型研发方面的实力。","https:\u002F\u002F36kr.com\u002Fnewsflashes\u002F3778928879129865?f=rss","5e4fd3d1-9cb4-44a6-bae5-9ffb449c05c1",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":21,"name":22,"slug":22,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"cc5242f5-02d8-4c4d-8359-d8f3561b43c9","en","ByteDance's Seed3D 2.0 pushes 3D generation forward","ByteDance recently released Seed3D 2.0, a new generation of 3D generation large model that uses a MoE architecture and sparse expert routing. The design expands parameter count and resolution while controlling inference compute, delivering richer texture detail and more precise metallic-roughness boundary generation.\n\n**Technical Innovation Highlights**\n\nSeed3D 2.0's core breakthrough lies in its Mixture of Experts architecture. Through sparse expert routing, the model maintains high precision while effectively controlling computational complexity. This design allows the model to handle more complex 3D scenes with significantly improved generation quality — especially in material representation and detail reproduction.\n\n**Strong Practical Value**\n\nCompared with traditional 3D generation models, Seed3D 2.0 brings major improvements in usability. The technical report shows significant gains in complex-scene rendering and detail representation, providing strong support for game development, virtual reality, and industrial design.\n\n**Pushing the Industry Ecosystem Forward**\n\nWith the API now live on Volcano Engine, Seed3D 2.0's release will accelerate the entire 3D content-generation ecosystem. Developers and enterprises will more easily access high-quality 3D generation capabilities, accelerating the adoption of 3D content across industries — and showcasing the strength of Chinese companies in fundamental AI model R&D.","bytedance-seed3d-2-0-moe-3d-generation","2026-04-23T02:06:00Z","2026-04-23T10:07:10.746610Z","2026-08-19T02:08:40.142862Z",true,"agent",240,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"eecebc53-86ab-4154-abb4-ab3982b70c4d","六巨头争锋：2026年4月LLM发布潮背后的技术变革","six-giants-llm-april-2026-gemini-claude-llama","2026-04-24T10:05:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"d8bc7b5e-9eb0-475e-91b7-5a3390d2c6a6","2026年开源LLM爆发：Meta、阿里、Google竞相发布新一代模型","open-source-llm-boom-2026-q1-meta-alibaba-google","2026-04-24T04:06:08+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"bbedb317-c221-43e3-b9a4-61798ed17b55","Voxtral 3:Mistral 语音智能体全栈,一轮对话不到一秒","voxtral-3-voice-agent-sdk","2026-10-21T23:11:24+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"a491d4db-2d5a-4723-b093-28d1512fd647","VLA-Δ:物理状态变化当监督信号,LIBERO 98.4","vla-delta-physical-state-transition","2026-10-20T19:07:27+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"b44fb160-9027-44cd-b355-a66869004abc","Nemotron 3.5 Super VL 开源:120B 总参只激活 12B","nemotron-3-5-super-vl-open-120b-moe","2026-10-20T17:11:56+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"faf5c85e-ed83-432a-8b55-80c9356862c5","腾讯优图开源5B全模态解析:文档榜96.96超GPT-5.2","youtu-parsing-omni-5b","2026-10-19T19:09:27+00:00"]